Methods › Computer Vision › Image Models › SANet

Self-Attention Network

SANet

11 papers tagged archive 2025-07-28

Introduced by Hengshuang Zhao et al. in Exploring Self-attention for Image Recognition

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Self-Attention Network (SANet) proposes two variations of self-attention used for image recognition: 1) pairwise self-attention which generalizes standard dot-product attention and is fundamentally a set operator, and 2) patchwise self-attention which is strictly more powerful than convolution.

PaperSource

Papers archive 2025-07-28

11 shown of 11, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 21 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Segmentation2
Semantic Segmentation2
Style Transfer2
Super-Resolution2
Camera Localization1
Crowd Counting1
Deblurring1
Decoder1
Denoising1
GPU1
Image Dehazing1
Image Restoration1
Image Super-Resolution1
Real-Time Semantic Segmentation1
Representation Learning1
Scene Recognition1
Scene Understanding1
Scheduling1
Self-Driving Cars1
Stereo Matching1

Usage over time archive 2025-07-28

Papers per year tagged with SANet: 2020 to 2023, peak 4 4 0 2020: 1 paper 2020 2021: 4 papers 2021 2022: 2 papers 2022 2023: 4 papers 2023
Papers per year the archive tags with this method, by the paper's archive date (11 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Image Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections